Skip to content

Read-only version: For security reasons, the Research Information System (FIS) has been temporarily replaced by this read-only version. All public content and full texts remain available; login, editing, submission and statistics are not available. Questions: fis@uni-bamberg.de

Home › Publications › Assessing State-of-the-Art Sentiment Models on State-of-the-Art Sentiment Datasets

Publication

Assessing State-of-the-Art Sentiment Models on State-of-the-Art Sentiment Datasets

Barnes, Jeremy; Klinger, Roman; Schulte im Walde, Sabine (2017): Assessing State-of-the-Art Sentiment Models on State-of-the-Art Sentiment Datasets, in: Alexandra Balahur, Saif M. Mohammad, Erik van der Goot, u. a. (Hrsg.), Proceedings of the 8th Workshop on Computational Approaches to Subjectivity, Sentiment and Social Media Analysis, Association for Computational Linguistics, S. 2–12, doi: 10.18653/v1/W17-5202.

Details

Faculty/Chair
Faculty/Professorship
Author
Barnes, Jeremy
Schulte im Walde, Sabine
Title of the compilation
Proceedings of the 8th Workshop on Computational Approaches to Subjectivity, Sentiment and Social Media Analysis
Editors
Balahur, Alexandra
Mohammad, Saif M.
Goot, Erik van der
Conference
8th Workshop on Computational Approaches to Subjectivity, Sentiment and Social Media Analysis, Copenhagen, Denmark
Publisher Information
Association for Computational Linguistics
Year of publication
2017
Language
English
DOI
URL
Abstract

There has been a good amount of progress in sentiment analysis over the past 10 years, including the proposal of new methods and the creation of benchmark datasets. In some papers, however, there is a tendency to compare models only on one or two datasets, either because of time restraints or because the model is tailored to a specific task. Accordingly, it is hard to understand how well a certain model generalizes across different tasks and datasets. In this paper, we contribute to this situation by comparing several models on six different benchmarks, which belong to different domains and additionally have different levels of granularity (binary, 3-class, 4-class and 5-class). We show that Bi-LSTMs perform well across datasets and that both LSTMs and Bi-LSTMs are particularly good at fine-grained sentiment tasks (i.e., with more than two classes). Incorporating sentiment information into word embeddings during training gives good results for datasets that are lexically similar to the training data. With our experiments, we contribute to a better understanding of the performance of different model architectures on different data sets. Consequently, we detect novel state-of-the-art results on the SenTube datasets.

GND Keywords
Computerlinguistik
Keywords
State-of-the-Art Sentiment Models
DDC Classification
004 Computer science
RVK Classification
ST 306
Peer Reviewed
yes
International Distribution
yes
Open Access Journal
yes
Type
Conferenceobject
URI
Activation date
2024-03-13

Permalink: https://fis.uni-bamberg.de/handle/uniba/93977 · Data as JSON · Cite: BibTeX · RIS

Data as of: 2026-11-16

Restricted read-only access: login, editing and submission are temporarily disabled.